© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 22221
    Prev
    Next
    INDEX
    Explanations

    materials, substances, and items used in manufacturing, production, or processing

    oai_token-act-pair · gpt-3.5-turbo

    references to materials and substances used in food production and their applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aez
    -0.83
    Ability
    -0.79
    reon
    -0.76
    uckland
    -0.74
    ocious
    -0.71
    icipated
    -0.71
    nesday
    -0.70
    isen
    -0.70
    PsyNetMessage
    -0.70
    Hunt
    -0.69
    POSITIVE LOGITS
     plastics
    1.45
     cosmetics
    1.44
     paints
    1.41
     lubric
    1.38
     perfume
    1.30
     shampoo
    1.27
     fabrics
    1.26
     powd
    1.26
     aeros
    1.22
     insulation
    1.20
    Activations Density 0.301%

    No Known Activations